What is it about?

In this paper, we present a software system called Courier that is responsible for optimally distributing the invocations of the functions within the heterogeneous FaaS deployments. We demonstrate and evaluate the functioning of Courier on three HeteroFaaSDs using three FaaS platforms: 1) on-premise OpenWhisk, 2) AWS Lambda, and 3) Google Cloud Functions (GCF). We show that Courier can improve the overall performance of the invocations of the functions within a HeteroFaaSD as compared to traditional load balancing algorithms.

Featured Image

Why is it important?

With the advent of serverless computing in diverse domains such as big data, machine learning, web applications, and edge computing there is a growing need for dynamic adaption to handle such diverse and heterogeneous functions. However, serverless computing is currently limited to homogeneous Function-as-a-Service (FaaS) deployments or simply FaaS Deployment (FaaSD) consisting of deployments of serverless functions using a FaaS platform in a region with certain memory configurations. In this work, we extend serverless computing to support Heterogeneous FaaS Deployments (HeteroFaaSDs) consisting of multiple FaaSDs with variable configurations (FaaS platform, region, and memory) and dynamically load balancing the invocations of the functions across these FaaSDs within a HeteroFaaSD to provide an optimal way for handling such serverless functions.

Perspectives

Writing this article was a great pleasure as it has co-authors with whom I have had long standing collaborations. This article is a part of the research which we are doing at Technical University of Munich, Germany on Function Delivery Network (FDN). If you want to know more, check this out: https://fdn.caps.in.tum.de/

Anshul Jindal
Technische Universitat Munchen Universitatsbibliothek Teilbibliothek Stammgelande

Read the Original

This page is a summary of: Courier, December 2021, ACM (Association for Computing Machinery),
DOI: 10.1145/3468737.3494097.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page